Pub Date : 2019-12-01DOI: 10.1109/icces48960.2019.9068105
{"title":"Session AI2: Artificial Intelligence II","authors":"","doi":"10.1109/icces48960.2019.9068105","DOIUrl":"https://doi.org/10.1109/icces48960.2019.9068105","url":null,"abstract":"","PeriodicalId":136643,"journal":{"name":"2019 14th International Conference on Computer Engineering and Systems (ICCES)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131338991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICCES48960.2019.9068111
Nesma El-Sokkary, A. Arafa, Ahmed H. Asad, H. Hefny
the majority cancer mortality among women is due to breast cancer over the world wide. Recent researches have shown the effectiveness of x-ray mammography in early detection of breast cancer. Unfortunately, the present systems for early detection are expensive and needs extremely complex algorithms. The crucial challenge in designing a computer-aided detection (CAD) systems for breast cancer are the segmentation phase, which requires highly complex computation. Hence, this paper proposes a CAD system to be utilized for breast cancer detection in mammographic datasets. The segmentation step is performed by a Particle Swarm Optimization Algorithm (PSO). Statistical, textural and shape feature are calculated over the segmented region. A non linear support vector machine (SVM) is exploited in the next phase in order to analyze the extracted features and classify the mammograms into normal, benign or malignant. For the sack of evaluating the performance, the experiment is performed on Mini-MIAS database. The obtained accuracy rates based on 10-folds cross validation are 85.4% for classifying normal from abnormal, 89.5% for classifying malignant from benign. The experiment shows that the classification accuracy is 81% when classifying normal, malignant or benign. The result compromises with recent researches concurs that the proposed algorithm compromises between the achieved accuracy to complexity cost.
{"title":"A Computer Aided Detection System for Breast Cancer in the MammogramsBased on Particle Swarm Optimization Algorithm","authors":"Nesma El-Sokkary, A. Arafa, Ahmed H. Asad, H. Hefny","doi":"10.1109/ICCES48960.2019.9068111","DOIUrl":"https://doi.org/10.1109/ICCES48960.2019.9068111","url":null,"abstract":"the majority cancer mortality among women is due to breast cancer over the world wide. Recent researches have shown the effectiveness of x-ray mammography in early detection of breast cancer. Unfortunately, the present systems for early detection are expensive and needs extremely complex algorithms. The crucial challenge in designing a computer-aided detection (CAD) systems for breast cancer are the segmentation phase, which requires highly complex computation. Hence, this paper proposes a CAD system to be utilized for breast cancer detection in mammographic datasets. The segmentation step is performed by a Particle Swarm Optimization Algorithm (PSO). Statistical, textural and shape feature are calculated over the segmented region. A non linear support vector machine (SVM) is exploited in the next phase in order to analyze the extracted features and classify the mammograms into normal, benign or malignant. For the sack of evaluating the performance, the experiment is performed on Mini-MIAS database. The obtained accuracy rates based on 10-folds cross validation are 85.4% for classifying normal from abnormal, 89.5% for classifying malignant from benign. The experiment shows that the classification accuracy is 81% when classifying normal, malignant or benign. The result compromises with recent researches concurs that the proposed algorithm compromises between the achieved accuracy to complexity cost.","PeriodicalId":136643,"journal":{"name":"2019 14th International Conference on Computer Engineering and Systems (ICCES)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115379256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICCES48960.2019.9068176
Nora Shoaip, S. Barakat, Mohammed M Elmogy
In the near future, the elderly will occupy nearly a quarter of the world's population. Such a percentage poses a significant challenge to face diseases related to this age, including Alzheimer's disease (AD), which is responsible for the destruction of brain cells and memory. This paper is our first step toward comprehensive research in the Alzheimer management system. It related to AD knowledge structures and semantic reasoning by using ontology. There is a necessary need to coordinate strategies that reuse existing ontology to support and enhance knowledge resources around the world. So we aim to reuse existing ontology and ensure comprehensive integration between them to improve the accuracy of reasoning. We propose Alzheimer's Disease Integrated Ontology (ADIO) that is intended to integrate two important biomedical ontologies for AD researches (i) Alzheimer's disease ontology (ADO) and (ii) AD Map Ontology (ADMO). ADO was described in OWL format and related to clinical, preclinical, experimental, and molecular mechanisms. ADMO represents the complexity of AD pathophysiology and more specific for the description of biological systems. So ADO and ADMO are relevant complements with each other, and their integration can increase the satisfaction of AD knowledge resources. As a result, HermiT 1.4.3.456 reasoner in Protégé provides checking of AD I 0 consistency, and the results of DLQuery show that ADIO is reliable and effective.
{"title":"Alzheimer's Disease Integrated Ontology (ADIO)","authors":"Nora Shoaip, S. Barakat, Mohammed M Elmogy","doi":"10.1109/ICCES48960.2019.9068176","DOIUrl":"https://doi.org/10.1109/ICCES48960.2019.9068176","url":null,"abstract":"In the near future, the elderly will occupy nearly a quarter of the world's population. Such a percentage poses a significant challenge to face diseases related to this age, including Alzheimer's disease (AD), which is responsible for the destruction of brain cells and memory. This paper is our first step toward comprehensive research in the Alzheimer management system. It related to AD knowledge structures and semantic reasoning by using ontology. There is a necessary need to coordinate strategies that reuse existing ontology to support and enhance knowledge resources around the world. So we aim to reuse existing ontology and ensure comprehensive integration between them to improve the accuracy of reasoning. We propose Alzheimer's Disease Integrated Ontology (ADIO) that is intended to integrate two important biomedical ontologies for AD researches (i) Alzheimer's disease ontology (ADO) and (ii) AD Map Ontology (ADMO). ADO was described in OWL format and related to clinical, preclinical, experimental, and molecular mechanisms. ADMO represents the complexity of AD pathophysiology and more specific for the description of biological systems. So ADO and ADMO are relevant complements with each other, and their integration can increase the satisfaction of AD knowledge resources. As a result, HermiT 1.4.3.456 reasoner in Protégé provides checking of AD I 0 consistency, and the results of DLQuery show that ADIO is reliable and effective.","PeriodicalId":136643,"journal":{"name":"2019 14th International Conference on Computer Engineering and Systems (ICCES)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114404265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICCES48960.2019.9068107
Mohamed Ismail Ibrahim, Dina M. Ellaithy
This paper exploits the efficient performing of the Multiple Input Multiple Output (MIMO)-Alamouti scheme for spectrum sensing in cognitive radio (CR). Consequently, enhancement in the overall performance and the detection probability by using the MIMO-Alamouti scheme is achieved. Moreover, at low signal-to-noise ratio (SNR), the cooperative spectrum distinguishing algorithm among the different spectrum distinguishing techniques is employed to raise the probability of detection and also solving the hidden node problem. Matlab software is used to simulate the detection probability versus SNR for different schemes. Up to 50% enhancement in detection probability (Pd) as compared with the conventional technique under signal to noise ratio (SNR) equals −15 dB and false alarm probability (Pf) equals 0.1. As compared with the common spectrum sensing approach in case of the majority rule, at least 10% advance in the probability of detection at false alarm probability equals 0.1 under SNR equals −10 dB and the number of secondary user (SU) equals 5.
{"title":"Improvement the Performing of Spectrum Distinguishing in Cognitive Radio using MIMO-Alamouti Scheme","authors":"Mohamed Ismail Ibrahim, Dina M. Ellaithy","doi":"10.1109/ICCES48960.2019.9068107","DOIUrl":"https://doi.org/10.1109/ICCES48960.2019.9068107","url":null,"abstract":"This paper exploits the efficient performing of the Multiple Input Multiple Output (MIMO)-Alamouti scheme for spectrum sensing in cognitive radio (CR). Consequently, enhancement in the overall performance and the detection probability by using the MIMO-Alamouti scheme is achieved. Moreover, at low signal-to-noise ratio (SNR), the cooperative spectrum distinguishing algorithm among the different spectrum distinguishing techniques is employed to raise the probability of detection and also solving the hidden node problem. Matlab software is used to simulate the detection probability versus SNR for different schemes. Up to 50% enhancement in detection probability (Pd) as compared with the conventional technique under signal to noise ratio (SNR) equals −15 dB and false alarm probability (Pf) equals 0.1. As compared with the common spectrum sensing approach in case of the majority rule, at least 10% advance in the probability of detection at false alarm probability equals 0.1 under SNR equals −10 dB and the number of secondary user (SU) equals 5.","PeriodicalId":136643,"journal":{"name":"2019 14th International Conference on Computer Engineering and Systems (ICCES)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124037094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICCES48960.2019.9068129
Eman Elemam, Ayman M. Bahaa-Eldin, N. Shaker, Mohamed Sobh
The Message Queue Telemetry Transport (MQTT) application layer protocol is widely used in Internet of Things (IoT) platforms. The MQTT standard has no mandatory requirements regarding the security services. A telemedicine is one of the IoT applications that mandates a critical level of security especially when it comes to human life. In this work, the weaknesses of MQTT are addressed and a modified protocol is proposed. This protocol mandates security aspects such as authentication, key exchange, and confidentiality. The protocol is proved to achieve its claims and is incorporated into a telemedicine environment as a critical environment for security.
{"title":"A Secure MQTT Protocol, Telemedicine IoT Case Study","authors":"Eman Elemam, Ayman M. Bahaa-Eldin, N. Shaker, Mohamed Sobh","doi":"10.1109/ICCES48960.2019.9068129","DOIUrl":"https://doi.org/10.1109/ICCES48960.2019.9068129","url":null,"abstract":"The Message Queue Telemetry Transport (MQTT) application layer protocol is widely used in Internet of Things (IoT) platforms. The MQTT standard has no mandatory requirements regarding the security services. A telemedicine is one of the IoT applications that mandates a critical level of security especially when it comes to human life. In this work, the weaknesses of MQTT are addressed and a modified protocol is proposed. This protocol mandates security aspects such as authentication, key exchange, and confidentiality. The protocol is proved to achieve its claims and is incorporated into a telemedicine environment as a critical environment for security.","PeriodicalId":136643,"journal":{"name":"2019 14th International Conference on Computer Engineering and Systems (ICCES)","volume":"16 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116341831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICCES48960.2019.9068110
Taha Emara, H. Afify, F. H. Ismail, A. Hassanien
Deep learning architectures, especially deep convolutional neural networks (CNN) achieve high accuracy on object classification and localization tasks. Achieving such high accuracy requires powerful devices. In this paper, rather than an ensemble of multiple complex models, a single Inception-v4 model is adapted to classify extracted from the HAM10000 dataset. The proposed model is enhanced by employing feature reuse using long residual connection in which the features extracted from earlier layers are concatenated with the high-level layers to increase the model classification performance. The dataset used in this study is imbalanced; therefore, a data sampling approach is used to mitigate the data imbalance effect. The proposed architecture achieves an accuracy of 94.7% using the provided test set at the official benchmark for the International Skin Imaging Collaboration (ISIC) 2018.
{"title":"A Modified Inception-v4 for Imbalanced Skin Cancer Classification Dataset","authors":"Taha Emara, H. Afify, F. H. Ismail, A. Hassanien","doi":"10.1109/ICCES48960.2019.9068110","DOIUrl":"https://doi.org/10.1109/ICCES48960.2019.9068110","url":null,"abstract":"Deep learning architectures, especially deep convolutional neural networks (CNN) achieve high accuracy on object classification and localization tasks. Achieving such high accuracy requires powerful devices. In this paper, rather than an ensemble of multiple complex models, a single Inception-v4 model is adapted to classify extracted from the HAM10000 dataset. The proposed model is enhanced by employing feature reuse using long residual connection in which the features extracted from earlier layers are concatenated with the high-level layers to increase the model classification performance. The dataset used in this study is imbalanced; therefore, a data sampling approach is used to mitigate the data imbalance effect. The proposed architecture achieves an accuracy of 94.7% using the provided test set at the official benchmark for the International Skin Imaging Collaboration (ISIC) 2018.","PeriodicalId":136643,"journal":{"name":"2019 14th International Conference on Computer Engineering and Systems (ICCES)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122879039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICCES48960.2019.9068163
R. Shalaby, George A. Adib, Y. Sabry, Michael Gad, D. Khalil, Y. Sabry, D. Khalil
Silicon photonics is continuing to develop for an increasing number of applications including data centers, miniaturized sensors and atomic clocks. The development involved the creation of the technology platform, design of innovative devices and developing models and methods for fabrication tolerance assessment. In our work, we suggest a novel structure for silicon photonic coupled-ring-resonator with an order of scale difference in the rings' lengths and sensitivity analysis for this structure. The design consists of a long racetrack resonator of length 472.6 µm (sub-millimeter scale) nested by ring resonator of radius 25 µm, This radius was chosen to minimize bending losses. The coupling ratio of the directional couplers is designed to be 97/3. The suggested structure is fabricated by the IMEC fabrication facility which is using DUV lithography and silicon etching ePIXfab. The analysis shows that this structure can achieve higher finesse than the typical values of the conventional structure, even with reasonable fabrication tolerance. Experimentally a finesse of about 25 and a quality factor of about 17,000 is achieved. The proposed structure can improve the performance of optical sensing and filtering.
{"title":"Silicon photonic coupled-ring resonator in nested configuration comprising different length scales","authors":"R. Shalaby, George A. Adib, Y. Sabry, Michael Gad, D. Khalil, Y. Sabry, D. Khalil","doi":"10.1109/ICCES48960.2019.9068163","DOIUrl":"https://doi.org/10.1109/ICCES48960.2019.9068163","url":null,"abstract":"Silicon photonics is continuing to develop for an increasing number of applications including data centers, miniaturized sensors and atomic clocks. The development involved the creation of the technology platform, design of innovative devices and developing models and methods for fabrication tolerance assessment. In our work, we suggest a novel structure for silicon photonic coupled-ring-resonator with an order of scale difference in the rings' lengths and sensitivity analysis for this structure. The design consists of a long racetrack resonator of length 472.6 µm (sub-millimeter scale) nested by ring resonator of radius 25 µm, This radius was chosen to minimize bending losses. The coupling ratio of the directional couplers is designed to be 97/3. The suggested structure is fabricated by the IMEC fabrication facility which is using DUV lithography and silicon etching ePIXfab. The analysis shows that this structure can achieve higher finesse than the typical values of the conventional structure, even with reasonable fabrication tolerance. Experimentally a finesse of about 25 and a quality factor of about 17,000 is achieved. The proposed structure can improve the performance of optical sensing and filtering.","PeriodicalId":136643,"journal":{"name":"2019 14th International Conference on Computer Engineering and Systems (ICCES)","volume":"88 17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126310871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/icces48960.2019.9068177
{"title":"Session MS: Modeling and Simulation","authors":"","doi":"10.1109/icces48960.2019.9068177","DOIUrl":"https://doi.org/10.1109/icces48960.2019.9068177","url":null,"abstract":"","PeriodicalId":136643,"journal":{"name":"2019 14th International Conference on Computer Engineering and Systems (ICCES)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125869318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：